JP6975073B2 - Forecasting systems, forecasting methods, and programs - Google Patents

Forecasting systems, forecasting methods, and programs Download PDF

Info

Publication number
JP6975073B2
JP6975073B2 JP2018033366A JP2018033366A JP6975073B2 JP 6975073 B2 JP6975073 B2 JP 6975073B2 JP 2018033366 A JP2018033366 A JP 2018033366A JP 2018033366 A JP2018033366 A JP 2018033366A JP 6975073 B2 JP6975073 B2 JP 6975073B2
Authority
JP
Japan
Prior art keywords
input
value
factory
unit
power consumption
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
JP2018033366A
Other languages
Japanese (ja)
Other versions
JP2019148999A (en
Inventor
哲平 手島
智之 榎本
秀伸 大津
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Mitsubishi Heavy Industries Ltd
Original Assignee
Mitsubishi Heavy Industries Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Mitsubishi Heavy Industries Ltd filed Critical Mitsubishi Heavy Industries Ltd
Priority to JP2018033366A priority Critical patent/JP6975073B2/en
Priority to US16/971,996 priority patent/US20200380393A1/en
Priority to EP19760182.6A priority patent/EP3745344A4/en
Priority to PCT/JP2019/005430 priority patent/WO2019167656A1/en
Priority to TW108105771A priority patent/TWI756515B/en
Publication of JP2019148999A publication Critical patent/JP2019148999A/en
Application granted granted Critical
Publication of JP6975073B2 publication Critical patent/JP6975073B2/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/12—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load
    • H02J3/14—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load by switching loads on to, or off from, network, e.g. progressively balanced loading
    • H02J3/144—Demand-response operation of the power transmission or distribution network
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/04—Manufacturing
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2310/00—The network for supplying or distributing electric power characterised by its spatial reach or by the load
    • H02J2310/50—The network for supplying or distributing electric power characterised by its spatial reach or by the load for selectively controlling the operation of the loads
    • H02J2310/56—The network for supplying or distributing electric power characterised by its spatial reach or by the load for selectively controlling the operation of the loads characterised by the condition upon which the selective controlling is based
    • H02J2310/58—The condition being electrical
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B70/00—Technologies for an efficient end-user side electric power management and consumption
    • Y02B70/30—Systems integrating technologies related to power network operation and communication or information technologies for improving the carbon footprint of the management of residential or tertiary loads, i.e. smart grids as climate change mitigation technology in the buildings sector, including also the last stages of power distribution and the control, monitoring or operating management systems at local level
    • Y02B70/3225—Demand response systems, e.g. load shedding, peak shaving
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y02B90/20—Smart grids as enabling technology in buildings sector
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S20/00—Management or operation of end-user stationary applications or the last stages of power distribution; Controlling, monitoring or operating thereof
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S20/00—Management or operation of end-user stationary applications or the last stages of power distribution; Controlling, monitoring or operating thereof
    • Y04S20/20—End-user application control systems
    • Y04S20/222—Demand response systems, e.g. load shedding, peak shaving

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Power Engineering (AREA)
  • Business, Economics & Management (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • General Business, Economics & Management (AREA)
  • Quality & Reliability (AREA)
  • Manufacturing & Machinery (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computational Linguistics (AREA)
  • Medical Informatics (AREA)
  • Primary Health Care (AREA)
  • Development Economics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Automation & Control Theory (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • General Factory Administration (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Description

本発明は、予測システム、予測方法、およびプログラムに関する。 The present invention relates to prediction systems, prediction methods, and programs.

特許文献１には、多数の製造ラインを備えた工場群のトータルの電力需要を予測する技術が開示されている。 Patent Document 1 discloses a technique for predicting the total power demand of a factory group having a large number of production lines.

特開２００４−１２９３２２号公報Japanese Unexamined Patent Publication No. 2004-129322

特許文献１に記載の技術においては、製造ラインそれぞれについて予め操業スケジュールが電力管理用計算機システムにインプットされ、電力管理用計算機システムは、当該操業スケジュールに基づいて、複数の製造ラインそれぞれのエネルギー需要を求める。特許文献１によれば、電力管理用計算機システムによって予測された電力需要が契約電力の上限を超える場合に、電力使用制限がなされる。他方、工場の管理者等においては、予め電力需要が契約電力の上限を超えないように操業計画を立てたいという要望がある。 In the technique described in Patent Document 1, an operation schedule is input to the power management computer system in advance for each production line, and the power management computer system determines the energy demand of each of the plurality of production lines based on the operation schedule. Ask. According to Patent Document 1, when the power demand predicted by the power management computer system exceeds the upper limit of the contracted power, the power usage is restricted. On the other hand, there is a request from factory managers and the like to make an operation plan in advance so that the electric power demand does not exceed the upper limit of the contracted electric power.

特許文献１に記載の技術において、操業計画を変更して再度エネルギー需要を求めるためには、管理者等は、すべての製造ラインについての細かな操業計画を電力管理用計算機システムにインプットする必要がある。しかしながら、製造ラインの数が多量である場合、再計算のために入力すべき操業計画の情報量が多くなるため、管理者等の負担が大きくなる。 In the technology described in Patent Document 1, in order to change the operation plan and obtain the energy demand again, the manager or the like needs to input the detailed operation plan for all the production lines into the computer system for power management. be. However, when the number of production lines is large, the amount of information on the operation plan to be input for recalculation increases, which increases the burden on the manager and the like.

負荷の大きい設備の操業計画に基づいて計算を行うようにシミュレータを設計することも考えられるが、予めどの設備の負荷が大きいかが分からない場合、シミュレータを設計することができない。
本発明の目的は、複数の設備を備える工場において、任意の設備の稼働に係る説明変数の入力に基づいて、工場の稼働を予測することができる予測システム、予測方法、およびプログラムを提供することにある。特に、工場のエネルギー需要を予測することができる予測システム、予測方法、およびプログラムを提供することにある。 It is conceivable to design the simulator so that the calculation is performed based on the operation plan of the equipment with a heavy load, but if it is not known in advance which equipment has a heavy load, the simulator cannot be designed.
An object of the present invention is to provide a prediction system, a prediction method, and a program capable of predicting the operation of a factory having a plurality of facilities based on the input of explanatory variables related to the operation of any facility. It is in. In particular, it is to provide forecasting systems, forecasting methods, and programs that can forecast factory energy demand.

本発明の第１の態様によれば、予測システムは、工場の稼働に係る複数の説明変数候補の中から少なくとも１つの説明変数候補の選択を受け付ける選択部と、選択された前記説明変数候補に係る値の入力を受け付ける値入力部と、入力された前記値を用い、選択されなかった前記説明変数候補の値を用いずに、前記工場の稼働に係る目的変数の値を特定する特定部と特定した前記目的変数の値を出力する出力部とを備える。 According to the first aspect of the present invention, the prediction system has a selection unit that accepts selection of at least one explanatory variable candidate from a plurality of explanatory variable candidates related to the operation of the factory, and the selected explanatory variable candidate . A value input unit that accepts the input of the relevant value, and a specific unit that specifies the value of the objective variable related to the operation of the factory by using the input value and without using the value of the explanatory variable candidate that was not selected. It is provided with an output unit that outputs the value of the specified objective variable.

本発明の第２の態様によれば、第１の態様に係る予測システムにおいて、前記工場の稼働に係る目的変数の値は、前記工場のエネルギー需要に係る値であるものであってよい。 According to the second aspect of the present invention, in the prediction system according to the first aspect, the value of the objective variable related to the operation of the factory may be the value related to the energy demand of the factory.

本発明の第３の態様によれば、第１または第２の態様に係る予測システムが、工場の稼働に係る複数の説明変数候補の値と前記工場の稼働に係る少なくとも１つの目的変数の値とのセットを含む履歴データを記憶する記憶部と、前記履歴データに基づいて、選択された前記説明変数を入力とし、前記目的変数を出力とするモデルのパラメータを学習する学習部と、を備え、前記特定部は、入力された前記値を学習された前記モデルに入力することで、前記目的変数の値を特定するものであってよい。 According to the third aspect of the present invention, the prediction system according to the first or second aspect has the values of a plurality of explanatory variable candidates related to the operation of the factory and the values of at least one objective variable related to the operation of the factory. It is provided with a storage unit for storing historical data including a set of the above, and a learning unit for learning the parameters of a model in which the selected explanatory variable is input and the objective variable is output based on the historical data. The specific unit may specify the value of the objective variable by inputting the input value into the trained model.

本発明の第４の態様によれば、第３の態様に係る予測システムにおいて、前記記憶部が記憶する、前記工場の稼働に係る複数の説明変数候補の値と前記工場の稼働に係る少なくとも１つの目的変数の値とのセットは、前記工場の稼働に係る複数の説明変数候補の値と前記工場のエネルギー需要に係る少なくとも１つの目的変数の値とのセットであり、前記モデルが出力する前記目的変数の値は、前記工場のエネルギー需要に係る値であってよい。 According to the fourth aspect of the present invention, in the prediction system according to the third aspect, the values of the plurality of explanatory variable candidates related to the operation of the factory and at least one related to the operation of the factory stored in the storage unit. The set with the value of one objective variable is a set of the value of a plurality of explanatory variable candidates related to the operation of the factory and the value of at least one objective variable related to the energy demand of the factory, and is output by the model. The value of the objective variable may be a value related to the energy demand of the factory.

本発明の第５の態様によれば、第１から第３の何れかの態様に係る予測システムが、前記履歴データに追加する説明変数候補の値の入力を受け付ける候補入力部を備えるものであってよい。 According to the fifth aspect of the present invention, the prediction system according to any one of the first to third aspects includes a candidate input unit that accepts input of the value of the explanatory variable candidate to be added to the historical data. It's okay.

本発明の第６の態様によれば、第１から第５の何れかの態様に係る予測システムにおいて、前記値入力部は、前記説明変数に係る値の時系列の入力を受け付けるものであってよい。 According to the sixth aspect of the present invention, in the prediction system according to any one of the first to fifth aspects, the value input unit accepts time-series input of values related to the explanatory variables. good.

本発明の第７の態様によれば、第６の態様に係る予測システムが、前記説明変数に係る値の時系列における単位時間の変更を受け付ける単位時間変更部をさらに備えるものであってよい。 According to the seventh aspect of the present invention, the prediction system according to the sixth aspect may further include a unit time change unit that accepts a change in the unit time in the time series of the value according to the explanatory variable.

本発明の第８の態様によれば、第１から第７の何れかの態様に係る予測システムにおいて、前記出力部は、特定した前記目的変数の値と、前記履歴データに含まれる前記目的変数の値または前記目的変数の比較値とを含む表示画面を出力するものであってよい。 According to the eighth aspect of the present invention, in the prediction system according to any one of the first to seventh aspects, the output unit has the specified value of the objective variable and the objective variable included in the historical data. A display screen including the value of or the comparison value of the objective variable may be output.

本発明の第９の態様によれば、第１から第８の何れかの態様に係る予測システムにおいて、前記入力部は、複数の工場における選択された前記説明変数に係る値の入力を受け付け、前記特定部は、入力された前記値に基づいて複数の工場の稼働に係る目的変数の値を統合した値を特定するものであってよい。 According to the ninth aspect of the present invention, in the prediction system according to any one of the first to eighth aspects, the input unit accepts input of a value related to the selected explanatory variable in a plurality of factories. The specific unit may specify a value obtained by integrating the values of the objective variables related to the operation of a plurality of factories based on the input values.

本発明の第１０の態様によれば、予測方法は、工場の稼働に係る複数の説明変数候補の中から少なくとも１つの説明変数候補の選択を受け付けるステップと、選択された前記説明変数候補に係る値の入力を受け付けるステップと、入力された前記値を用い、選択されなかった前記説明変数候補の値を用いずに、前記工場の稼働に係る目的変数の値を特定するステップと特定した前記目的変数の値を出力するステップとを含む。 According to the tenth aspect of the present invention, the prediction method relates to a step of accepting selection of at least one explanatory variable candidate from a plurality of explanatory variable candidates related to the operation of the factory, and the selected explanatory variable candidate . The purpose specified as a step of accepting the input of a value and a step of specifying the value of the objective variable related to the operation of the factory using the input value and without using the value of the explanatory variable candidate that was not selected. Includes a step to output the value of a variable.

本発明の第１１の態様によれば、第１０の態様に係る予測方法において、前記工場の稼働に係る目的変数の値は、前記工場のエネルギー需要に係る値であってよい。 According to the eleventh aspect of the present invention, in the prediction method according to the tenth aspect, the value of the objective variable related to the operation of the factory may be the value related to the energy demand of the factory.

本発明の第１２の態様によれば、プログラムは、コンピュータに、工場の稼働に係る複数の説明変数候補の中から少なくとも１つの説明変数候補の選択を受け付けるステップと、選択された前記説明変数候補に係る値の入力を受け付けるステップと、入力された前記値を用い、選択されなかった前記説明変数候補の値を用いずに、前記工場の稼働に係る目的変数の値を特定するステップと特定した前記目的変数の値を出力するステップとを実行させる。 According to the twelfth aspect of the present invention, the program accepts the computer to select at least one explanatory variable candidate from the plurality of explanatory variable candidates related to the operation of the factory, and the selected explanatory variable candidate. It was specified as a step of accepting the input of the value related to the above and a step of specifying the value of the objective variable related to the operation of the factory by using the input value and not using the value of the explanatory variable candidate which was not selected. The step of outputting the value of the objective variable is executed.

本発明の第１３の態様によれば、第１２の態様に係るプログラムにおいて、前記工場の稼働に係る目的変数の値は、前記工場のエネルギー需要に係る値であってよい。 According to the thirteenth aspect of the present invention, in the program according to the twelfth aspect, the value of the objective variable related to the operation of the factory may be the value related to the energy demand of the factory.

上記態様のうち少なくとも１つの態様によれば、エネルギー需要予測システムは、複数の設備を備える工場において、任意の設備の稼働に係る説明変数の入力に基づいて、工場のエネルギー需要を予測することができる。 According to at least one aspect of the above, the energy demand forecasting system can predict the energy demand of a factory equipped with a plurality of facilities based on the input of explanatory variables related to the operation of any facility. can.

第１の実施形態に係るエネルギー需要予測システムの構成を示す概略図である。It is a schematic diagram which shows the structure of the energy demand forecasting system which concerns on 1st Embodiment. 第１の実施形態に係るエネルギー需要予測装置の構成を示す概略ブロック図である。It is a schematic block diagram which shows the structure of the energy demand forecasting apparatus which concerns on 1st Embodiment. 第１の実施形態に係るエネルギー需要予測装置の動作を示すフローチャートである。It is a flowchart which shows the operation of the energy demand forecasting apparatus which concerns on 1st Embodiment. 説明変数の選択画面の例を示す図である。It is a figure which shows the example of the selection screen of an explanatory variable. 操業計画の入力画面の例を示す図である。It is a figure which shows the example of the input screen of the operation plan. 第１の実施形態に係るエネルギー需要の予測結果の出力画面の例である。This is an example of an output screen of the energy demand forecast result according to the first embodiment. 第２の実施形態に係るエネルギー需要の予測結果の出力画面の例である。This is an example of an output screen of the energy demand forecast result according to the second embodiment. 少なくとも１つの実施形態に係るコンピュータの構成を示す概略ブロック図である。It is a schematic block diagram which shows the structure of the computer which concerns on at least one Embodiment.

〈定義〉
本明細書において「特定する」とは、第１の値を用いて複数の値を取り得る第２の値を定めることである。例えば、「特定する」は、第１の値から第２の値を算出すること、テーブルを参照して第１の値に対応する第２の値を読み出すこと、第１の値をクエリとして第２の値を検索すること、第１の値に基づいて複数の候補の中から第２の値を選択すること、第１の値から第２の値を推定・予測することを含む。
「取得する」とは、新たに値を得ることである。例えば、「取得する」は、値を受信すること、値の入力を受け付けること、テーブルから値を読み出すこと、ある値から他の値を算出することを含む。 <Definition>
As used herein, "specifying" means using the first value to determine a second value that can take a plurality of values. For example, "specify" means to calculate a second value from a first value, to refer to a table to read a second value corresponding to the first value, and to use the first value as a query. It includes searching for a value of 2, selecting a second value from a plurality of candidates based on the first value, and estimating / predicting a second value from the first value.
To "acquire" is to obtain a new value. For example, "acquiring" includes receiving a value, accepting a value input, reading a value from a table, and calculating another value from one value.

〈第１の実施形態〉
以下、図面を参照しながら実施形態について詳しく説明する。
図１は、第１の実施形態に係るエネルギー需要予測システムの構成を示す概略図である。
エネルギー需要予測システム１は、複数の設備Ｅを備える工場Ｆと、エネルギー需要予測装置１０とを備える。
各設備Ｅは、外部から供給される電力によって稼働する。各設備Ｅは、操業計画に従って稼働し、また停止する。操業計画には、設備の稼働時間帯および稼働日に係る情報が含まれる。つまり操業計画は、設備Ｅの稼働状態の時系列である。
エネルギー需要予測装置１０は、各設備Ｅの操業計画と各設備Ｅの消費電力の実績値と工場Ｆ全体の消費電力の実績値とに基づいて、工場Ｆのエネルギー需要を予測する。各設備Ｅの消費電力の実績値は、例えば設備Ｅに設けられた図示しないセンサによって検出される。ここでは、工場Ｆの設備Ｅの稼働に係る情報が工場の稼働に係る説明変数候補であり、工場Ｆのエネルギー需要が工場の稼働に係る目的変数である。 <First Embodiment>
Hereinafter, embodiments will be described in detail with reference to the drawings.
FIG. 1 is a schematic diagram showing a configuration of an energy demand forecasting system according to a first embodiment.
The energy demand forecasting system 1 includes a factory F including a plurality of facilities E and an energy demand forecasting device 10.
Each facility E is operated by electric power supplied from the outside. Each facility E operates and shuts down according to the operation plan. The operation plan includes information on the operating hours and working days of the equipment. That is, the operation plan is a time series of the operating state of the equipment E.
The energy demand forecasting device 10 predicts the energy demand of the factory F based on the operation plan of each facility E, the actual value of the power consumption of each facility E, and the actual value of the power consumption of the entire factory F. The actual value of the power consumption of each equipment E is detected by, for example, a sensor (not shown) provided in the equipment E. Here, the information related to the operation of the equipment E of the factory F is an explanatory variable candidate related to the operation of the factory, and the energy demand of the factory F is the objective variable related to the operation of the factory.

《エネルギー需要予測装置の構成》
図２は、第１の実施形態に係るエネルギー需要予測装置の構成を示す概略ブロック図である。
エネルギー需要予測装置１０は、履歴取得部１０１、履歴記憶部１０２、選択部１０３、モデル記憶部１０５、学習部１０４、計画入力部１０６、エネルギー需要特定部１０７、出力部１０８、候補入力部１０９、単位時間変更部１１０を備える。 << Configuration of energy demand forecaster >>
FIG. 2 is a schematic block diagram showing the configuration of the energy demand forecasting device according to the first embodiment.
The energy demand forecasting device 10 includes a history acquisition unit 101, a history storage unit 102, a selection unit 103, a model storage unit 105, a learning unit 104, a plan input unit 106, an energy demand specifying unit 107, an output unit 108, and a candidate input unit 109. A unit time changing unit 110 is provided.

履歴取得部１０１は、工場Ｆの各設備Ｅから、操業計画および消費電力の時系列を取得する。履歴取得部１０１は、操業計画を設備Ｅの制御装置から読み出してもよいし、工場Ｆの管理者等の利用者からの入力により取得してもよい。履歴取得部１０１は、消費電力を設備Ｅに設けられたセンサから取得する。複数の設備Ｅの操業計画、すなわち複数の設備Ｅの稼働時間帯および稼働日に係る情報は、工場の稼働に係る複数の説明変数候補の一例である。また、複数の設備Ｅの消費電力は、工場のエネルギー需要に係る目的変数の一例である。 The history acquisition unit 101 acquires an operation plan and a time series of power consumption from each equipment E of the factory F. The history acquisition unit 101 may read the operation plan from the control device of the equipment E, or may acquire the operation plan by input from a user such as a manager of the factory F. The history acquisition unit 101 acquires power consumption from a sensor provided in the equipment E. The operation plans of the plurality of facilities E, that is, the information on the operating hours and operating days of the plurality of facilities E are examples of the plurality of explanatory variable candidates related to the operation of the factory. Further, the power consumption of the plurality of facilities E is an example of the objective variable related to the energy demand of the factory.

履歴記憶部１０２は、履歴取得部１０１が取得した複数の設備Ｅの操業計画および消費電力の時系列を記憶する。 The history storage unit 102 stores the operation plans and the time series of power consumption of the plurality of facilities E acquired by the history acquisition unit 101.

選択部１０３は、利用者から、複数の設備Ｅの操業計画の中から少なくとも１つの説明変数の選択を受け付ける。例えば、利用者は、工場Ｆの稼働において消費電力の増減への影響度が高いと思われる１つまたは複数の設備Ｅの操業計画を説明変数として選択することができる。つまり、利用者は、エネルギー需要の予測のために、工場Ｆが備えるすべての設備Ｅの操業計画を入力する必要がない。このとき、利用者は、設備Ｅの稼働時間帯または稼働日の一方のみを説明変数として選択してもよい。 The selection unit 103 receives from the user the selection of at least one explanatory variable from the operation plans of the plurality of facilities E. For example, the user can select the operation plan of one or more facilities E, which are considered to have a high influence on the increase / decrease in power consumption in the operation of the factory F, as an explanatory variable. That is, the user does not need to input the operation plan of all the equipment E provided in the factory F in order to predict the energy demand. At this time, the user may select only one of the operating time zone or the operating day of the equipment E as an explanatory variable.

モデル記憶部１０５は、操業計画に基づいて工場Ｆの総消費電力を特定するために用いられるモデルを記憶する。モデル記憶部１０５が記憶するモデルの例としては、ニューラルネットワークモデルやベイジアンモデルなどが挙げられる。 The model storage unit 105 stores a model used to specify the total power consumption of the factory F based on the operation plan. Examples of the model stored in the model storage unit 105 include a neural network model and a Bayesian model.

学習部１０４は、履歴記憶部１０２が記憶する情報を教師データとして、利用者に選択された設備Ｅに係る操業計画を入力とし、工場Ｆの総消費電力の時系列を出力とするように、モデル記憶部１０５が記憶するモデルを学習させる。すなわち、学習部１０４は、履歴記憶部１０２が記憶する情報に基づいて、モデル記憶部１０５が記憶するモデルにパラメータを割り当てる。 The learning unit 104 uses the information stored in the history storage unit 102 as teacher data, inputs the operation plan related to the equipment E selected by the user, and outputs the time series of the total power consumption of the factory F. The model stored in the model storage unit 105 is trained. That is, the learning unit 104 assigns parameters to the model stored in the model storage unit 105 based on the information stored in the history storage unit 102.

計画入力部１０６は、利用者から、選択された設備Ｅに係る操業計画の入力を受け付ける。 The plan input unit 106 receives input of an operation plan related to the selected equipment E from the user.

エネルギー需要特定部１０７は、計画入力部１０６に入力された操業計画を、モデル記憶部１０５が記憶するモデルに入力することで、工場Ｆの総消費電力の時系列を特定する。つまり、エネルギー需要特定部１０７は、工場Ｆが備える一部の設備Ｅに係る操業計画に基づいて、工場Ｆ全体のエネルギー需要を予測する。以下、エネルギー需要特定部１０７が特定した総消費電力の時系列を、予測エネルギー需要ともよぶ。 The energy demand specifying unit 107 specifies the time series of the total power consumption of the factory F by inputting the operation plan input to the plan input unit 106 into the model stored in the model storage unit 105. That is, the energy demand specifying unit 107 predicts the energy demand of the entire factory F based on the operation plan of a part of the equipment E provided in the factory F. Hereinafter, the time series of the total power consumption specified by the energy demand specifying unit 107 is also referred to as a predicted energy demand.

出力部１０８は、エネルギー需要特定部１０７が特定した工場Ｆの総消費電力を出力する。 The output unit 108 outputs the total power consumption of the factory F specified by the energy demand specifying unit 107.

候補入力部１０９は、工場Ｆの設備Ｅのうち、履歴記憶部１０２に操業計画が記憶されていない設備Ｅに係る操業計画の入力を受け付ける。候補入力部１０９に入力された操業計画は、新たな説明変数候補として履歴記憶部１０２に記憶される。これにより、説明変数候補の数を増加させることができる。 The candidate input unit 109 accepts the input of the operation plan related to the equipment E in which the operation plan is not stored in the history storage unit 102 among the equipment E of the factory F. The operation plan input to the candidate input unit 109 is stored in the history storage unit 102 as a new explanatory variable candidate. This makes it possible to increase the number of explanatory variable candidates.

単位時間変更部１１０は、各設備Ｅの操業計画における稼働時間帯の単位時間の変更を受け付ける。例えば、履歴記憶部１０２が記憶する操業計画について稼働時間帯が１時間単位で設定されている場合に、単位時間変更部１１０は、利用者の入力に従って、計画入力部１０６に入力する操業計画の稼働時間帯の単位時間を３時間単位に変更することができる。 The unit time changing unit 110 accepts a change in the unit time of the operating time zone in the operation plan of each facility E. For example, when the operating time zone is set in units of one hour for the operation plan stored in the history storage unit 102, the unit time changing unit 110 inputs the operation plan to the plan input unit 106 according to the input of the user. The unit time of the operating time zone can be changed to 3 hours.

《エネルギー需要予測装置の動作》
図３は、第１の実施形態に係るエネルギー需要予測装置の動作を示すフローチャートである。
エネルギー需要予測装置１０の履歴取得部１０１は、エネルギー需要の予測処理の実施前に、工場Ｆの各設備Ｅから操業計画および消費電力を取得し、履歴記憶部１０２に記録しておく。 << Operation of energy demand forecaster >>
FIG. 3 is a flowchart showing the operation of the energy demand forecasting device according to the first embodiment.
The history acquisition unit 101 of the energy demand forecasting device 10 acquires an operation plan and power consumption from each facility E of the factory F and records them in the history storage unit 102 before executing the energy demand forecasting process.

エネルギー需要の予測処理を開始すると、エネルギー需要予測装置１０の選択部１０３は、説明変数候補である設備Ｅの一覧を含む説明変数の選択画面を表示する（ステップＳ１）。図４は、説明変数の選択画面の例を示す図である。説明変数の選択画面には、各設備Ｅについて、名称と定格出力とチェックボックスとが表示される。選択部１０３は、利用者から、エネルギー需要の予測処理における説明変数に用いる設備Ｅの選択を受け付ける（ステップＳ２）。利用者は、説明変数に用いる設備Ｅの欄のチェックボックスをオンにすることで、説明変数に用いる設備Ｅを選択する。また、利用者は、各説明変数候補の名称および定格出力を書き換えてもよい。また、利用者は、設備Ｅの欄のチェックボックスをオフにすることで、オフにされたチェックボックスに係る設備Ｅを選択から外し、結果として説明変数から外すことができる。 When the energy demand forecasting process is started, the selection unit 103 of the energy demand forecasting device 10 displays an explanatory variable selection screen including a list of equipment E which is an explanatory variable candidate (step S1). FIG. 4 is a diagram showing an example of an explanatory variable selection screen. On the explanatory variable selection screen, the name, rated output, and check box are displayed for each equipment E. The selection unit 103 receives from the user the selection of the equipment E to be used as the explanatory variable in the energy demand forecast processing (step S2). The user selects the equipment E to be used as the explanatory variable by selecting the check box in the column of the equipment E to be used as the explanatory variable. In addition, the user may rewrite the name and rated output of each explanatory variable candidate. Further, the user can remove the equipment E related to the unchecked check box from the selection by clearing the check box in the column of the equipment E, and as a result, can remove it from the explanatory variables.

選択部１０３が設備Ｅの選択を受け付けると、学習部１０４は、履歴記憶部１０２が記憶する情報を教師データとして、利用者に選択された設備Ｅに係る操業計画を入力とし、工場Ｆの総消費電力の時系列を出力とするように、モデル記憶部１０５が記憶するモデルを学習させる（ステップＳ３）。これにより、エネルギー需要予測装置１０は、利用者が選択した設備Ｅの操業計画に基づいて工場Ｆの総消費電力を予測するためのモデルを生成することができる。学習部１０４が設備Ｅの選択結果に基づいてモデルを学習することで、エネルギー需要予測装置１０は、選択されなかった設備Ｅについて操業計画が入力されなくても、各設備Ｅが停止しているものとみなされずに適切に工場Ｆの総消費電力を予測することができる。 When the selection unit 103 accepts the selection of the equipment E, the learning unit 104 inputs the information stored in the history storage unit 102 as the teacher data and the operation plan related to the equipment E selected by the user as the input, and the total of the factory F. The model stored in the model storage unit 105 is trained so that the time series of power consumption is output (step S3). As a result, the energy demand forecasting device 10 can generate a model for predicting the total power consumption of the factory F based on the operation plan of the equipment E selected by the user. By learning the model based on the selection result of the equipment E by the learning unit 104, the energy demand forecasting device 10 stops each equipment E even if the operation plan is not input for the equipment E that is not selected. The total power consumption of the factory F can be appropriately predicted without being regarded as a thing.

次に、計画入力部１０６は、選択された各設備Ｅに係る操業計画の入力画面を表示する（ステップＳ４）。つまり、計画入力部１０６は、稼働時間帯の入力画面および稼働日の入力画面を画面に表示する。図５は、操業計画の入力画面の例を示す図である。操業計画の入力画面には、選択された各設備Ｅの複数の時間帯または複数の日付について、稼働か停止かを表すチェックボックスが表示される。計画入力部１０６は、利用者から、選択された各設備Ｅに係る操業計画の入力を受け付ける（ステップＳ５）。利用者は、各設備Ｅについて、時間帯または日付に係るチェックボックスのオン／オフを組み合わせることで、各設備Ｅの操業計画を入力する。 Next, the plan input unit 106 displays an operation plan input screen for each selected facility E (step S4). That is, the plan input unit 106 displays the input screen of the operating time zone and the input screen of the operating day on the screen. FIG. 5 is a diagram showing an example of an operation plan input screen. On the operation plan input screen, a check box indicating whether to operate or stop is displayed for a plurality of time zones or a plurality of dates of each selected facility E. The plan input unit 106 receives input of an operation plan related to each selected facility E from the user (step S5). The user inputs the operation plan of each equipment E by combining the on / off of the check boxes related to the time zone or the date for each equipment E.

エネルギー需要特定部１０７は、計画入力部１０６に入力された操業計画を、モデル記憶部１０５が記憶するモデルに入力することで、工場Ｆの総消費電力の時系列（予測エネルギー需要Ｅ１）を特定する（ステップＳ６）。出力部１０８は、エネルギー需要特定部１０７が特定した予測エネルギー需要Ｅ１を出力する（ステップＳ７）。図６は、第１の実施形態に係るエネルギー需要の予測結果の出力画面の例である。出力部１０８は、エネルギー需要特定部１０７が特定した予測エネルギー需要Ｅ１に加え、履歴記憶部１０２が記憶する消費電力の時系列（実測エネルギー需要Ｅ２）と、工場Ｆの契約電力値Ｔｈ（目的変数の比較値）とを出力する。これにより、利用者は、予測エネルギー需要Ｅ１と実測エネルギー需要Ｅ２との乖離を視認することができ、また工場Ｆの総消費電力が将来的に契約電力値Ｔｈを超えるか否かを視認することができる。 The energy demand specifying unit 107 specifies the time series (predicted energy demand E1) of the total power consumption of the factory F by inputting the operation plan input to the plan input unit 106 into the model stored in the model storage unit 105. (Step S6). The output unit 108 outputs the predicted energy demand E1 specified by the energy demand specifying unit 107 (step S7). FIG. 6 is an example of an output screen of the energy demand forecast result according to the first embodiment. In addition to the predicted energy demand E1 specified by the energy demand specifying unit 107, the output unit 108 includes a time series of power consumption (measured energy demand E2) stored in the history storage unit 102 and a contract power value Th (objective variable) of the factory F. (Comparison value of) and is output. As a result, the user can visually check the difference between the predicted energy demand E1 and the measured energy demand E2, and also visually check whether the total power consumption of the factory F exceeds the contract power value Th in the future. Can be done.

なお、予測エネルギー需要Ｅ１と実測エネルギー需要Ｅ２との乖離が大きい場合、利用者は、説明変数に用いる設備Ｅを追加し、または変更することで、予測エネルギー需要Ｅ１と実測エネルギー需要Ｅ２との乖離が小さくなるように、モデルを再学習させることができる。これにより、利用者は、工場Ｆにおいて総消費電力の支配因子となる設備Ｅを特定することができる。 If the divergence between the predicted energy demand E1 and the measured energy demand E2 is large, the user can add or change the equipment E used as an explanatory variable to diverge between the predicted energy demand E1 and the measured energy demand E2. The model can be retrained so that Thereby, the user can specify the equipment E which is the controlling factor of the total power consumption in the factory F.

また、予測エネルギー需要Ｅ１が契約電力値Ｔｈを超える場合、利用者は操業計画を変更し、再度エネルギー需要予測装置１０にエネルギー需要を予測させることができる。この際、全ての設備についての操業計画を入力する必要がないため、利用者は、エネルギー需要の予測のための操業計画の変更を容易に実施することができる。 Further, when the predicted energy demand E1 exceeds the contract power value Th, the user can change the operation plan and have the energy demand forecasting device 10 predict the energy demand again. At this time, since it is not necessary to input the operation plan for all the facilities, the user can easily change the operation plan for forecasting the energy demand.

また、利用者は、エネルギー需要予測装置１０にさらに精度よくエネルギー需要の予測をさせたい場合、説明変数候補を追加することができる。候補入力部１０９は、利用者から新たな説明変数候補に係る操業計画の入力を受け付けると、これを履歴記憶部１０２に記録する。その後、学習部１０４は、モデル記憶部１０５が記憶するモデルを、追加された説明変数候補に係る操業計画を用いて学習させることができる。 Further, the user can add explanatory variable candidates when he / she wants the energy demand forecasting device 10 to predict the energy demand more accurately. When the candidate input unit 109 receives the input of the operation plan related to the new explanatory variable candidate from the user, the candidate input unit 109 records this in the history storage unit 102. After that, the learning unit 104 can train the model stored in the model storage unit 105 by using the operation plan related to the added explanatory variable candidate.

また、利用者は、ステップＳ５における操業計画の入力項目が多く煩雑である場合に、またより細かに操業計画を指定したい場合に、操業計画の単位時間を変更することができる。単位時間変更部１１０は、利用者から変更後の単位時間の入力を受け付ける。単位時間変更部１１０は、履歴記憶部１０２が記憶する操業計画を、入力された単位時間に係る操業計画に変換する。例えば、単位時間変更部１１０は、１時間単位の操業計画を３時間単位の操業計画に変更する。例えば、単位時間変更部１１０は、３時間単位のある時間帯において２時間が稼働を示し１時間が停止を示す場合など、変更後の単位時間に係る時間帯に異なる状態が含まれる場合、当該時間帯において少なくとも稼働が含まれていれば当該時間帯の設備Ｅの状態を稼働状態に決定してもよいし、稼働と停止のうち多い方の状態を適用してもよいし、当該時間帯において少なくとも停止が含まれていれば当該時間帯の設備Ｅの状態を停止状態に決定してもよい。単位時間変更部１１０が単位時間の変更を受け付けると、計画入力部１０６は、変更後の単位時間に係る操業計画の入力画面を表示する。 Further, the user can change the unit time of the operation plan when the input items of the operation plan in step S5 are many and complicated, or when he / she wants to specify the operation plan in more detail. The unit time changing unit 110 receives input of the changed unit time from the user. The unit time changing unit 110 converts the operation plan stored in the history storage unit 102 into an operation plan related to the input unit time. For example, the unit time changing unit 110 changes the operation plan of one hour unit to the operation plan of three hours unit. For example, when the unit time changing unit 110 includes a different state in the time zone related to the changed unit time, such as when the operation is shown for 2 hours and the unit time is stopped for 1 hour in a certain time zone of 3 hours. If at least the operation is included in the time zone, the state of the equipment E in the time zone may be determined as the operating state, or the state of the more of the operation and the stop may be applied, or the state of the equipment E in the time zone may be applied. If at least the stoppage is included in the above, the state of the equipment E in the time zone may be determined to be the stop state. When the unit time changing unit 110 accepts the change of the unit time, the plan input unit 106 displays the input screen of the operation plan related to the changed unit time.

《作用・効果》
このように、第１の実施形態によれば、エネルギー需要予測システム１は、工場Ｆの複数の設備Ｅの中から少なくとも１つの設備Ｅの選択を受け付け、選択された設備Ｅに係る操業計画の入力を受け付ける。そして、エネルギー需要予測システム１は、入力された操業計画に基づいて工場Ｆの総消費電力を特定する。これにより、利用者は、複数の設備Ｅを備える工場Ｆにおいて、任意の設備Ｅの操業計画について入力することで、工場Ｆ全体のエネルギー需要を得ることができる。したがって、工場Ｆが備える設備Ｅの数によらず、利用者にとって操業計画の入力が煩雑にならない。 《Action / Effect》
As described above, according to the first embodiment, the energy demand forecasting system 1 accepts the selection of at least one equipment E from the plurality of equipment E of the factory F, and the operation plan for the selected equipment E. Accept input. Then, the energy demand forecast system 1 specifies the total power consumption of the factory F based on the input operation plan. As a result, the user can obtain the energy demand of the entire factory F by inputting the operation plan of any facility E in the factory F provided with the plurality of facilities E. Therefore, regardless of the number of facilities E provided in the factory F, the input of the operation plan is not complicated for the user.

〈第２の実施形態〉
第１の実施形態に係るエネルギー需要予測システム１は、１つの工場Ｆについての総消費電力を算出する。ところで、電力の契約は、必ずしも工場単位でなされるとは限らず、複数の工場Ｆについて一の契約電力が定められる可能性がある。この場合、複数の工場Ｆの稼働日や稼働時間帯をずらす運用がとられることがある。つまり、一の工場Ｆの情報に基づいて他の工場を制御することや、複数の工場Ｆの情報を相互に参照して工場Ｆ全体を制御することなどがなされている。そこで、第２の実施形態に係るエネルギー需要予測システム１は、複数の工場Ｆに係る総消費電力を算出する。 <Second embodiment>
The energy demand forecasting system 1 according to the first embodiment calculates the total power consumption for one factory F. By the way, the electric power contract is not always made for each factory, and there is a possibility that one contract electric power is set for a plurality of factories F. In this case, the operation may be performed by shifting the operating days and operating hours of the plurality of factories F. That is, it is possible to control another factory based on the information of one factory F, or to control the entire factory F by mutually referring to the information of a plurality of factories F. Therefore, the energy demand forecasting system 1 according to the second embodiment calculates the total power consumption related to the plurality of factories F.

第２の実施形態に係るエネルギー需要予測装置１０の構成は、第１の実施形態と同様である。このとき、履歴取得部１０１は、複数の工場Ｆの各設備Ｅから操業計画および消費電力の時系列を取得する。利用者は、複数の工場Ｆの複数の設備Ｅから、説明変数に係る設備Ｅを選択する。このとき、一部の工場Ｆについて設備Ｅが選択されなくてもよい。学習部１０４は、選択された設備Ｅに係る操業計画を入力とし、全工場Ｆの総消費電力を出力とするように、モデルを学習させる。エネルギー需要特定部１０７は、入力された操業計画に基づいて、全工場Ｆの総消費電力すなわち予測エネルギー需要Ｅ１を特定する。出力部１０８は、エネルギー需要特定部１０７が特定した全工場Ｆの予測エネルギー需要Ｅ１を出力する。図７は、第２の実施形態に係るエネルギー需要の予測結果の出力画面の例である。出力部１０８は、エネルギー需要特定部１０７が特定した予測エネルギー需要Ｅ１に加え、履歴記憶部１０２が記憶する工場Ｆごとの消費電力の時系列（実測エネルギー需要Ｅ２）と、契約電力値Ｔｈとを出力する。 The configuration of the energy demand forecasting device 10 according to the second embodiment is the same as that of the first embodiment. At this time, the history acquisition unit 101 acquires the operation plan and the time series of power consumption from each equipment E of the plurality of factories F. The user selects the equipment E related to the explanatory variables from the plurality of equipments E of the plurality of factories F. At this time, the equipment E may not be selected for some factories F. The learning unit 104 trains the model so that the operation plan related to the selected equipment E is input and the total power consumption of all the factories F is output. The energy demand specifying unit 107 specifies the total power consumption of all the factories F, that is, the predicted energy demand E1 based on the input operation plan. The output unit 108 outputs the predicted energy demand E1 of all the factories F specified by the energy demand specifying unit 107. FIG. 7 is an example of an output screen of the energy demand forecast result according to the second embodiment. In addition to the predicted energy demand E1 specified by the energy demand specifying unit 107, the output unit 108 stores the time series of power consumption for each factory F (measured energy demand E2) stored in the history storage unit 102 and the contracted power value Th. Output.

なお、第２の実施形態に係るエネルギー需要予測システム１は、選択された設備Ｅに係る操業計画を入力とし、全工場Ｆの総消費電力を出力とするようにモデルを学習させ、これにより全工場Ｆの総消費電力を特定するが、これに限られない。例えば、他の実施形態に係るエネルギー需要予測システム１は、選択された設備Ｅに係る操業計画を入力とし、各工場Ｆの総消費電力を出力とするようにモデルを学習させ、各工場の総消費電力の総和をとることで全工場Ｆの総消費電力を特定してもよい。 The energy demand forecasting system 1 according to the second embodiment takes the operation plan related to the selected equipment E as an input, and trains the model so that the total power consumption of all the factories F is output, thereby all. It specifies, but is not limited to, the total power consumption of factory F. For example, the energy demand forecasting system 1 according to another embodiment takes an operation plan related to the selected equipment E as an input, trains a model so as to output the total power consumption of each factory F, and makes the total power consumption of each factory output. The total power consumption of all factories F may be specified by taking the total power consumption.

以上、図面を参照して一実施形態について詳しく説明してきたが、具体的な構成は上述のものに限られることはなく、様々な設計変更等をすることが可能である。
例えば、上述した実施形態において、説明変数として各設備Ｅの操業計画を用いるが、これに限られない。例えば、他の実施形態においては、工場Ｆの生産計画、設備Ｅの機種、設備Ｅを操作する作業員の配置計画、工場Ｆのイベントカレンダーなどを説明変数に用いてもよい。 Although one embodiment has been described in detail with reference to the drawings, the specific configuration is not limited to the above-mentioned one, and various design changes and the like can be made.
For example, in the above-described embodiment, the operation plan of each facility E is used as an explanatory variable, but the present invention is not limited to this. For example, in other embodiments, the production plan of the factory F, the model of the equipment E, the allocation plan of the workers who operate the equipment E, the event calendar of the factory F, and the like may be used as explanatory variables.

また、上述の実施形態においては、予測システムがエネルギー需要を予測するエネルギー需要予測装置１０に実装される例について説明したが、これに限られず、他の実施形態に係る予測システムはエネルギー需要以外の目的変数を特定してもよい。例えば、他の実施形態においては、予測システムは、工場Ｆにおける製品の製造に係るパラメータを説明変数として用い、完成品に発生する不良箇所の数を目的変数としても良い。 Further, in the above-described embodiment, an example in which the forecasting system is mounted on the energy demand forecasting device 10 for predicting the energy demand has been described, but the present invention is not limited to this, and the forecasting systems according to other embodiments are other than the energy demand. The objective variable may be specified. For example, in another embodiment, the prediction system may use the parameters related to the manufacture of the product in the factory F as the explanatory variables and the number of defective parts generated in the finished product as the objective variable.

より詳細には、予測システムは、工場Ｆにおける完成品の不良箇所の数を予測するために、複数の製造工程のそれぞれについて少なくとも１つの製造に係るデータを取得する。予測システムは、これらのデータの一部もしくは全てを説明変数として、工場Ｆのエネルギー需要の予測に代わり、完成品に発生する不良箇所の数を予測してもよい。この場合、完成品の完成に至る途中の製造工程における仕掛の段階で収集されるデータから、完成品の不良箇所の数を予測することが可能となる。途中の製造工程において完成品の不良箇所の数が所定の閾値を超えると予測される場合は、その仕掛品の製造を中止することで、その仕掛品に必要以上の工数や労力を割くことを抑制できるのみならず、工場にてその工数や労力のためのエネルギーを消費することを抑制することが可能となる。 More specifically, the prediction system acquires at least one manufacturing data for each of the plurality of manufacturing processes in order to predict the number of defective parts of the finished product in the factory F. The prediction system may use some or all of these data as explanatory variables to predict the number of defective parts generated in the finished product instead of predicting the energy demand of the factory F. In this case, it is possible to predict the number of defective parts of the finished product from the data collected at the in-process stage in the manufacturing process on the way to the completion of the finished product. If it is predicted that the number of defective parts of the finished product will exceed a predetermined threshold in the manufacturing process in the middle of the process, it is possible to discontinue the production of the work-in-process and devote more man-hours and labor to the work-in-process. Not only can it be suppressed, but it is also possible to suppress the consumption of energy for the man-hours and labor in the factory.

工場Ｆが鋳造工場である場合、複数の設備による複数の製造工程を経て完成品としての鋳造物ができあがる。各工程の仕掛品が各工程で定められている所定の公差や品質を満たしていても、最後の製造工程を経た後に、完成品に複数の不良箇所（表面の欠陥等）が発生することがある。これらの不良箇所は、通常は別途修正を施すが、不良箇所の数が過剰である場合、大幅な工数の増加となるため、望ましくない場合がある。予測システムは、各製造工程の製造に係るデータ、例えば製造工程の雰囲気温度、鋳造に係る速度・品質パラメータ・温度、材料の温度・品質パラメータ、各工程中で特定の作業に要した時間等を説明変数とし、完成品である鋳造物の不良箇所の数を目的変数とすることで、鋳造に係る製造工程の途中段階で、完成品の不良箇所の数を予測することができる。これにより、各工程の仕掛品が、各工程で定められている所定の公差や品質を満たしている場合でも、それまでの製造に係るデータに基づいて完成品の不良箇所の数が所定の閾値を超える場合、その仕掛品の製造を中止するという判断が可能となる。結果として、その仕掛品に以後の製造工程で必要以上の工数や労力を割くことを抑制し、工場にてエネルギーを消費することを抑制できる。 When the factory F is a casting factory, a casting as a finished product is completed through a plurality of manufacturing processes by a plurality of facilities. Even if the work-in-process of each process meets the specified tolerances and qualities specified in each process, multiple defective parts (surface defects, etc.) may occur in the finished product after the final manufacturing process. be. These defective parts are usually corrected separately, but if the number of defective parts is excessive, the man-hours will be significantly increased, which may not be desirable. The prediction system captures manufacturing data for each manufacturing process, such as atmospheric temperature in the manufacturing process, speed / quality parameter / temperature for casting, material temperature / quality parameter, and time required for a specific operation in each process. By setting the number of defective parts of the finished product as an explanatory variable and using the number of defective parts of the finished product as the objective variable, it is possible to predict the number of defective parts of the finished product in the middle of the manufacturing process related to casting. As a result, even if the work-in-process in each process meets the predetermined tolerances and qualities specified in each process, the number of defective parts in the finished product is a predetermined threshold based on the data related to the manufacturing up to that point. If it exceeds, it is possible to decide to discontinue the production of the work-in-process. As a result, it is possible to suppress the unnecessary man-hours and labors for the work-in-process in the subsequent manufacturing process, and to suppress the consumption of energy in the factory.

また、上記において説明変数に用いられるパラメータを製造工程の管理に利用することもできる。
より詳細には、不良箇所の数が所定の閾値を越える際に、不良箇所の数について寄与度の高い製造に係るパラメータが明らかになった場合、そのパラメータを管理することで、不良箇所の数が所定の閾値を越えることを抑制することも可能となる。
例えば、予測システムにおいて複数の説明変数候補から説明変数を選択する過程において、特定の製造工程の製造に係るデータ、例えば特定の製造工程の雰囲気温度が、完成品の不良箇所の数の予測時に最も寄与度の高いパラメータであり、その雰囲気温度が所定値以上になることで完成品の不良箇所の数が所定の閾値を越えることが明らかになった場合、管理者は、その製造工程の雰囲気温度を所定値以上にならないように管理することで、完成品の不良箇所の数が所定の閾値を越えないよう管理することが可能となる。これにより、不良箇所の修正に過剰な工数を割くことを抑制し、工場にて必要以上のエネルギーを消費することを抑制できる。この場合、管理するパラメータは１つである必要は無く、必要に応じて不良箇所の数の予測に寄与する複数のパラメータを管理しても良い。 Further, the parameters used for the explanatory variables in the above can also be used for controlling the manufacturing process.
More specifically, when the number of defective parts exceeds a predetermined threshold value, if a parameter related to manufacturing having a high contribution to the number of defective parts is clarified, the number of defective parts can be managed by managing the parameter. It is also possible to suppress that the value exceeds a predetermined threshold value.
For example, in the process of selecting explanatory variables from a plurality of explanatory variable candidates in a prediction system, data related to manufacturing of a specific manufacturing process, for example, the atmospheric temperature of a specific manufacturing process, is the most when predicting the number of defective parts of a finished product. If it is a parameter with a high degree of contribution and it becomes clear that the number of defective parts in the finished product exceeds a predetermined threshold when the atmospheric temperature exceeds a predetermined value, the manager can use the atmospheric temperature in the manufacturing process. By managing so that the value does not exceed a predetermined value, it is possible to manage the number of defective parts of the finished product so as not to exceed a predetermined threshold value. As a result, it is possible to suppress excessive man-hours for repairing defective parts and to suppress consumption of more energy than necessary in the factory. In this case, it is not necessary to manage one parameter, and a plurality of parameters that contribute to the prediction of the number of defective parts may be managed as needed.

なお、本実施形態における完成品は、製品としての完成品に限られず、工場Ｆにおいて対象としている複数の製造工程の最終成果物ではあるが、製品としては中間生成物であるものも含まれる。
また、予測システムは、目的変数として、不良箇所の数に代えて、不良品か良品かの判断結果を予測してもよい。製品の外観や形状不良を、不良品か良品かの判断基準とする場合、必ずしも完成品にて計測できるパラメータが存在するとは限らない。このような場合、予測システムは、例えば不良品を０、良品を１とするパラメータを目的変数することで、０以上、１以下の値となる予測値を得ることができる。管理者は、完成品の完成に至る途中の製造工程における仕掛品の段階で、この予測値が閾値より小さければ不良品である確率が高く、閾値より大きければ良品である確率が高いとして、完成品の品質を予想することができる。
また、予測システムは、目的変数として、不良箇所の数に代えて、不良箇所の場所または不良の種類を予測しても良い。すなわち、管理者は、予測システムに不良箇所の場所や不良の種類を学習させることで、完成品の所定の場所が不良になる確率、または完成品が所定の種類の不良となる確率を予測値として得ることができる。管理者は、予測システムが出力する予測値を参照することで、完成品の完成に至る途中の製造工程における仕掛品の段階で、完成品の品質を予想することができる。 The finished product in the present embodiment is not limited to the finished product as a product, and is the final product of a plurality of manufacturing processes targeted at the factory F, but the product also includes an intermediate product.
Further, the prediction system may predict the determination result of a defective product or a non-defective product instead of the number of defective parts as an objective variable. When the appearance or shape defect of a product is used as a criterion for judging whether it is a defective product or a non-defective product, there is not always a parameter that can be measured in the finished product. In such a case, the prediction system can obtain a predicted value having a value of 0 or more and 1 or less by, for example, setting a parameter of 0 for a defective product and 1 for a non-defective product as an objective variable. At the stage of work-in-process in the manufacturing process leading to the completion of the finished product, the manager considers that if this predicted value is smaller than the threshold value, the probability of being a defective product is high, and if it is larger than the threshold value, the probability of being a good product is high. The quality of the product can be predicted.
Further, the prediction system may predict the location of the defective portion or the type of the defect as the objective variable instead of the number of defective portions. That is, the manager makes the prediction system learn the location of the defective part and the type of defect, so that the probability that the predetermined place of the finished product becomes defective or the probability that the finished product becomes defective of the predetermined type is predicted. Can be obtained as. By referring to the predicted value output by the prediction system, the manager can predict the quality of the finished product at the stage of the work-in-process in the manufacturing process on the way to the completion of the finished product.

図８は、少なくとも１つの実施形態に係るコンピュータの構成を示す概略ブロック図である。
コンピュータ９０は、プロセッサ９１、メインメモリ９２、ストレージ９３、インタフェース９４を備える。
上述のエネルギー需要予測装置１０は、コンピュータ９０に実装される。そして、上述した各処理部の動作は、プログラムの形式でストレージ９３に記憶されている。プロセッサ９１は、プログラムをストレージ９３から読み出してメインメモリ９２に展開し、当該プログラムに従って上記処理を実行する。また、プロセッサ９１は、プログラムに従って、上述した履歴記憶部１０２に対応する記憶領域をメインメモリ９２に確保する。 FIG. 8 is a schematic block diagram showing the configuration of a computer according to at least one embodiment.
The computer 90 includes a processor 91, a main memory 92, a storage 93, and an interface 94.
The energy demand forecasting device 10 described above is mounted on the computer 90. The operation of each of the above-mentioned processing units is stored in the storage 93 in the form of a program. The processor 91 reads a program from the storage 93, expands it into the main memory 92, and executes the above processing according to the program. Further, the processor 91 secures a storage area corresponding to the above-mentioned history storage unit 102 in the main memory 92 according to the program.

ストレージ９３の例としては、ＨＤＤ（Hard Disk Drive）、ＳＳＤ（Solid State Drive）、磁気ディスク、光磁気ディスク、ＣＤ−ＲＯＭ（Compact Disc Read Only Memory）、ＤＶＤ−ＲＯＭ（Digital Versatile Disc Read Only Memory）、半導体メモリ等が挙げられる。ストレージ９３は、コンピュータ９０のバスに直接接続された内部メディアであってもよいし、インタフェース９４または通信回線を介してコンピュータ９０に接続される外部メディアであってもよい。また、このプログラムが通信回線によってコンピュータ９０に配信される場合、配信を受けたコンピュータ９０が当該プログラムをメインメモリ９２に展開し、上記処理を実行してもよい。少なくとも１つの実施形態において、ストレージ９３は、一時的でない有形の記憶媒体である。 Examples of the storage 93 include HDD (Hard Disk Drive), SSD (Solid State Drive), magnetic disk, magneto-optical disk, CD-ROM (Compact Disc Read Only Memory), and DVD-ROM (Digital Versatile Disc Read Only Memory). , Semiconductor memory and the like. The storage 93 may be an internal medium directly connected to the bus of the computer 90, or an external medium connected to the computer 90 via the interface 94 or a communication line. When this program is distributed to the computer 90 by a communication line, the distributed computer 90 may expand the program to the main memory 92 and execute the above process. In at least one embodiment, the storage 93 is a non-temporary tangible storage medium.

また、当該プログラムは、前述した機能の一部を実現するためのものであってもよい。さらに、当該プログラムは、前述した機能をストレージ９３に既に記憶されている他のプログラムとの組み合わせで実現するもの、いわゆる差分ファイル（差分プログラム）であってもよい。 Further, the program may be for realizing a part of the above-mentioned functions. Further, the program may be a so-called difference file (difference program) that realizes the above-mentioned function in combination with another program already stored in the storage 93.

１ エネルギー需要予測システム
１０ エネルギー需要予測装置
１０１ 履歴取得部
１０２ 履歴記憶部
１０３ 選択部
１０４ 学習部
１０５ モデル記憶部
１０６ 計画入力部
１０７ エネルギー需要特定部
１０８ 出力部
１０９ 候補入力部
１１０ 単位時間変更部
Ｅ 設備
Ｆ 工場
Ｅ１ 予測エネルギー需要
Ｅ２ 実測エネルギー需要
Ｔｈ 契約電力値 1 Energy demand forecast system 10 Energy demand forecaster 101 History acquisition unit 102 History storage unit 103 Selection unit 104 Learning unit 105 Model storage unit 106 Plan input unit 107 Energy demand specification unit 108 Output unit 109 Candidate input unit 110 Unit time change unit E Equipment F Factory E1 Forecast energy demand E2 Measured energy demand Th Contracted power value

Claims (8)

工場の複数の設備それぞれの操業計画と消費電力の値とのセットを含む履歴データを記憶する記憶部と、
工場の複数の設備の操業計画の中から少なくとも１つの設備の操業計画の選択を受け付ける選択部と、
前記履歴データに基づいて、選択された前記設備の操業計画を入力に含み、選択されなかった前記設備の操業計画を入力に含まず、前記工場全体の消費電力の値を出力とするモデルのパラメータを学習する学習部と、
選択された前記設備の操業計画に係る値の入力を受け付ける値入力部と、
入力された前記値を学習された前記モデルに入力することで、前記工場全体の消費電力の値を特定する特定部と、
特定した前記消費電力の値を出力する出力部と
を備える予測システム。 A storage unit that stores historical data including a set of operation plans and power consumption values for each of multiple facilities in the factory.
A selection unit that accepts the selection of an operation plan for at least one facility from the operation plans for multiple facilities in the factory.
Based on the historical data, the parameters of the model that include the operation plan of the selected equipment in the input, do not include the operation plan of the equipment that was not selected in the input, and output the value of the power consumption of the entire factory. With the learning department to learn
A value input unit that accepts input of values related to the operation plan of the selected equipment, and
By inputting the input value into the trained model, a specific unit that specifies the value of the power consumption of the entire factory and a specific unit.
A prediction system including an output unit that outputs the specified power consumption value. 前記履歴データに含まれない設備に係る操業計画であって前記履歴データに追加する操業計画の入力を受け付ける候補入力部を備える
請求項１に記載の予測システム。 It is provided with a candidate input unit that accepts input of an operation plan to be added to the history data , which is an operation plan related to the equipment not included in the history data.
The prediction system according to claim 1. 前記値入力部は、選択された前記設備の操業計画に係る値の時系列の入力を受け付ける
請求項１または請求項２に記載の予測システム。 The prediction system according to claim 1 or 2 , wherein the value input unit accepts time-series input of values related to the operation plan of the selected equipment. 選択された前記設備の操業計画に係る値の時系列における単位時間の変更を受け付ける単位時間変更部をさらに備える
請求項３に記載の予測システム。 Further provided with a unit time change unit that accepts changes in the unit time in the time series of the values related to the operation plan of the selected equipment.
The prediction system according to claim 3. 前記出力部は、特定した前記工場全体の消費電力の値と、前記履歴データが示す工場全体の消費電力の値または前記工場全体の消費電力の比較値とを含む表示画面を出力する
請求項１から請求項４の何れか１項に記載の予測システム。 The output unit outputs a display screen including the specified power consumption value of the entire factory and the power consumption value of the entire factory indicated by the historical data or the comparison value of the power consumption of the entire factory.
The prediction system according to any one of claims 1 to 4. 前記値入力部は、複数の工場における選択された前記設備の操業計画に係る値の入力を受け付け、
前記特定部は、入力された前記値に基づいて複数の工場全体の消費電力の値を統合した値を特定する
請求項１から請求項５の何れか１項に記載の予測システム。 The value input unit accepts input of values related to the operation plan of the selected equipment in a plurality of factories.
The prediction system according to any one of claims 1 to 5 , wherein the specific unit specifies a value obtained by integrating the power consumption values of a plurality of factories based on the input values. 工場の複数の設備の操業計画の中から少なくとも１つの設備の操業計画の選択を受け付けるステップと、
記憶部に記憶された工場の複数の設備それぞれの操業計画と消費電力の値とのセットを含む履歴データに基づいて、選択された前記設備の操業計画を入力に含み、選択されなかった前記設備の操業計画を入力に含まず、前記工場全体の消費電力の値を出力とするモデルのパラメータを学習するステップと、
選択された前記設備の操業計画に係る値の入力を受け付けるステップと、
入力された前記値を学習された前記モデルに入力することで、前記工場全体の消費電力の値を特定するステップと、
特定した前記消費電力の値を出力するステップと
を含む予測方法。 A step that accepts the selection of an operation plan for at least one facility from the operation plans for multiple facilities in the factory.
Based on historical data including a set of operation plans and power consumption values of each of the multiple facilities of the factory stored in the storage unit, the operation plans of the selected facilities are included in the input, and the facilities that are not selected are included in the input. The step of learning the parameters of the model that does not include the operation plan of the above in the input and outputs the value of the power consumption of the whole factory.
The step of accepting the input of the value related to the operation plan of the selected equipment, and
By inputting the input value into the trained model, the step of specifying the power consumption value of the entire factory and the step.
A prediction method including a step of outputting the specified power consumption value. コンピュータに、
工場の複数の設備の操業計画の中から少なくとも１つの設備の操業計画の選択を受け付けるステップと、
記憶部に記憶された工場の複数の設備それぞれの操業計画と消費電力の値とのセットを含む履歴データに基づいて、選択された前記設備の操業計画を入力に含み、選択されなかった前記設備の操業計画を入力に含まず、前記工場全体の消費電力の値を出力とするモデルのパラメータを学習するステップと、
選択された前記設備の操業計画に係る値の入力を受け付けるステップと、
入力された前記値を学習された前記モデルに入力することで、前記工場全体の消費電力の値を特定するステップと、
特定した前記消費電力の値を出力するステップと
を実行させるためのプログラム。 On the computer
A step that accepts the selection of an operation plan for at least one facility from the operation plans for multiple facilities in the factory.
Based on historical data including a set of operation plans and power consumption values of each of the multiple facilities of the factory stored in the storage unit, the operation plans of the selected facilities are included in the input, and the facilities that are not selected are included in the input. The step of learning the parameters of the model that does not include the operation plan of the above in the input and outputs the value of the power consumption of the whole factory.
The step of accepting the input of the value related to the operation plan of the selected equipment, and
By inputting the input value into the trained model, the step of specifying the power consumption value of the entire factory and the step.
A program for executing a step to output the specified power consumption value.
JP2018033366A 2018-02-27 2018-02-27 Forecasting systems, forecasting methods, and programs Active JP6975073B2 (en)

Priority Applications (5)

Application Number Priority Date Filing Date Title
JP2018033366A JP6975073B2 (en) 2018-02-27 2018-02-27 Forecasting systems, forecasting methods, and programs
US16/971,996 US20200380393A1 (en) 2018-02-27 2019-02-14 Prediction system, prediction method, and program
EP19760182.6A EP3745344A4 (en) 2018-02-27 2019-02-14 Prediction system, prediction method, and program
PCT/JP2019/005430 WO2019167656A1 (en) 2018-02-27 2019-02-14 Prediction system, prediction method, and program
TW108105771A TWI756515B (en) 2018-02-27 2019-02-21 Prediction system, prediction method, and program

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2018033366A JP6975073B2 (en) 2018-02-27 2018-02-27 Forecasting systems, forecasting methods, and programs

Publications (2)

Publication Number Publication Date
JP2019148999A JP2019148999A (en) 2019-09-05
JP6975073B2 true JP6975073B2 (en) 2021-12-01

Family

ID=67805352

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2018033366A Active JP6975073B2 (en) 2018-02-27 2018-02-27 Forecasting systems, forecasting methods, and programs

Country Status (5)

Country Link
US (1) US20200380393A1 (en)
EP (1) EP3745344A4 (en)
JP (1) JP6975073B2 (en)
TW (1) TWI756515B (en)
WO (1) WO2019167656A1 (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7424807B2 (en) * 2019-11-28 2024-01-30 ファナック株式会社 Machine learning device, power consumption prediction device, and control device
JP7408028B2 (en) 2021-12-21 2024-01-04 三菱電機株式会社 Power management support device, program and power management support method

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3498786B2 (en) * 1999-01-19 2004-02-16 住友金属工業株式会社 Power consumption prediction method
JP2004129322A (en) 2002-09-30 2004-04-22 Nippon Steel Corp Predictive control system for power demand
JP2004173342A (en) * 2002-11-18 2004-06-17 Hitachi Ltd Operation support system and operation support computer program
EP1967996A1 (en) * 2007-03-09 2008-09-10 Omron Corporation Factor estimating support device and method of controlling the same, and factor estimating support program
JP2015012753A (en) * 2013-07-01 2015-01-19 日新電設株式会社 On-demand type power control system, on-demand type power control method, and on-demand type power control program
US11593817B2 (en) * 2015-06-30 2023-02-28 Panasonic Intellectual Property Corporation Of America Demand prediction method, demand prediction apparatus, and non-transitory computer-readable recording medium
JP6327226B2 (en) * 2015-10-02 2018-05-23 Ｊｆｅスチール株式会社 Method and system for predicting power consumption
TWI580145B (en) * 2015-10-27 2017-04-21 財團法人資訊工業策進會 Electricity consumption predicting system and electricity consumption predicting method applied for processing machine
US10185298B2 (en) * 2016-03-29 2019-01-22 Applied Materials, Inc. Smart tool monitoring system
WO2017203601A1 (en) * 2016-05-24 2017-11-30 三井情報株式会社 Information processing device, information processing method, information processing system, and program
JP6086640B1 (en) 2016-08-31 2017-03-01 ユーシーシー上島珈琲株式会社 Method for producing coffee beverage

Also Published As

Publication number Publication date
US20200380393A1 (en) 2020-12-03
TW201939326A (en) 2019-10-01
EP3745344A4 (en) 2021-03-31
TWI756515B (en) 2022-03-01
EP3745344A1 (en) 2020-12-02
WO2019167656A1 (en) 2019-09-06
JP2019148999A (en) 2019-09-05

Similar Documents

Publication Publication Date Title
Duan et al. Selective maintenance scheduling under stochastic maintenance quality with multiple maintenance actions
CN109870903B (en) Parameter optimization method, device and non-transitory computer readable medium
JP2019182342A (en) Diagram analysis supporting device and method
JPWO2018220885A1 (en) Production plan creation device, production plan creation method, and production plan creation program
US7966151B2 (en) Method for analyzing operation of a machine
US20230046379A1 (en) Factory Management Device, Factory Management Method, and Factory Management Program
JP6975073B2 (en) Forecasting systems, forecasting methods, and programs
Erguido et al. After-sales services optimisation through dynamic opportunistic maintenance: a wind energy case study
Jain et al. Towards smart manufacturing with virtual factory and data analytics
JP6317910B2 (en) Parts equipment allocation device, parts equipment allocation method, and program
US10222788B2 (en) Plan generating device and plan generating method
TW202347062A (en) Method for waiting time prediction in semiconductor factory
Baumers et al. Developing an understanding of the cost of additive manufacturing
Levrat et al. Odds-based decision-making tool for opportunistic production-maintenance synchronization
WO2020175084A1 (en) Operation evaluation device, operation evaluation method, and program
CN114330816A (en) Industrial raw material purchasing control method and system
KR20170008632A (en) Method for demand forecasting of spare part
Tong et al. Forecasting field failure data for repairable systems using neural networks and SARIMA model
JP6917288B2 (en) Maintenance plan generation system
CN110858355A (en) Project budget balance prediction method and device
San Cristóbal A Cost Forecasting model for a Vessel drydocking
Olsson et al. Case-based reasoning applied to geometric measurements for decision support in manufacturing
JP6695298B2 (en) Order control device
Kiassat et al. Effects of operator learning on production output: a Markov chain approach
Kalinowski et al. The procedure of reaction to unexpected events in scheduling of manufacturing systems with discrete production flow

Legal Events

Date Code Title Description
A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20200825

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20201208

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20210205

A02 Decision of refusal

Free format text: JAPANESE INTERMEDIATE CODE: A02

Effective date: 20210706

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20210903

C60 Trial request (containing other claim documents, opposition documents)

Free format text: JAPANESE INTERMEDIATE CODE: C60

Effective date: 20210903

A911 Transfer to examiner for re-examination before appeal (zenchi)

Free format text: JAPANESE INTERMEDIATE CODE: A911

Effective date: 20210917

C21 Notice of transfer of a case for reconsideration by examiners before appeal proceedings

Free format text: JAPANESE INTERMEDIATE CODE: C21

Effective date: 20210921

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20211026

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20211105

R150 Certificate of patent or registration of utility model

Ref document number: 6975073

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R150